mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-02-01 13:11:39 +01:00
a3957bd3b3
This patch adds a simple Cortex-M4 schedule, renaming the existing M3 schedule to M4 and filling in the latencies as-per the Cortex-M4 TRM: https://developer.arm.com/docs/ddi0439/latest Most of these are 1, with the important exception being loads taking 2 cycles. A few others are also higher, but I don't believe they make a large difference. I've repurposed the M3 schedule as the latencies are mostly the same between the two cores, with the M4 having more FP and DSP instructions. We also turn on MISched and UseAA for the cores that now use this. It also adds some schedule Write's to various instruction to make things simpler. Differential Revision: https://reviews.llvm.org/D54142 llvm-svn: 360768
29 lines
932 B
LLVM
29 lines
932 B
LLVM
; RUN: llc < %s -mtriple=armv8r-eabi -mcpu=cortex-r52 | FileCheck %s --check-prefix=CHECK --check-prefix=USEAA
|
|
; RUN: llc < %s -mtriple=armv7m-eabi -mcpu=cortex-m4 | FileCheck %s --check-prefix=CHECK --check-prefix=USEAA
|
|
; RUN: llc < %s -mtriple=armv8m-eabi -mcpu=cortex-m33 | FileCheck %s --check-prefix=CHECK --check-prefix=USEAA
|
|
; RUN: llc < %s -mtriple=armv8r-eabi -mcpu=generic | FileCheck %s --check-prefix=CHECK --check-prefix=GENERIC
|
|
|
|
; Check we use AA during codegen, so can interleave these loads/stores.
|
|
|
|
; CHECK-LABEL: test
|
|
; GENERIC: ldr
|
|
; GENERIC: str
|
|
; GENERIC: ldr
|
|
; GENERIC: str
|
|
; USEAA: ldr
|
|
; USEAA: ldr
|
|
; USEAA: str
|
|
; USEAA: str
|
|
|
|
define void @test(i32* nocapture %a, i32* noalias nocapture %b) {
|
|
entry:
|
|
%0 = load i32, i32* %a, align 4
|
|
%add = add nsw i32 %0, 10
|
|
store i32 %add, i32* %a, align 4
|
|
%1 = load i32, i32* %b, align 4
|
|
%add2 = add nsw i32 %1, 20
|
|
store i32 %add2, i32* %b, align 4
|
|
ret void
|
|
}
|
|
|